Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

only run eval,but don't have ./checkpoints/tw2t_multi_reg-cla-gird #23

Open
JackKoLing opened this issue Oct 2, 2024 · 1 comment

Comments

@JackKoLing
Copy link

JackKoLing commented Oct 2, 2024

Thanks a great job. I want to run bash urbangpt_eval.sh, so I changed the setting from urbangpt_eval.sh. For example, output_model=./vicuna-7b-v1.5, which is a checkpoint download from huggingface, and I change the datapath and so on. By the way, I don't have ./checkpoints/tw2t_multi_reg-cla-gird. And then, I ran and got an error:
File "/nfs/code/LLMs/UrbanGPT/urbangpt/model/STLlama.py", line 123, in set_st_tower st_tower = st_tower.to(dtype=torch.float32) ^^^^^^^^^^^ AttributeError: 'NoneType' object has no attribute 'to'

I think the problem is output_model. Can anyone provide?

@JackKoLing JackKoLing changed the title st_tower = st_tower.to(dtype=torch.float32) only run eval,but don't have ./checkpoints/tw2t_multi_reg-cla-gird Oct 2, 2024
@LZH-YS1998
Copy link
Collaborator

Thanks for your attention. Please use the checkpoint of UrbanGPT for evaluation. If you want to train from scratch, you can use vicuna-7b-v1.5 as the base model.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants